dbea77e347* Studio: forward unknown CLI args directly to llama-server `unsloth studio run --model X --top-k 20 --chat-template-file foo.jinja` now passes the unknown flags through to the llama-server subprocess. Adds a denylist for flags Studio manages (port, -m, -c, --api-key, -ngl, --flash-attn, --no-context-shift, --jinja, GPU-fit, model-identity, ...) that returns HTTP 400 on collision. HTTP callers can supply the same list via LoadRequest.llama_extra_args. * Studio: accept `--model org/repo:variant` shorthand in `unsloth studio run` Mirrors llama.cpp's `-hf <repo>:<quant>` and ollama's pull syntax so `unsloth studio run --model unsloth/gpt-oss-20b-GGUF:UD-Q4_K_XL` is equivalent to `--model unsloth/... --gguf-variant UD-Q4_K_XL`. Local paths and Windows drive letters are preserved verbatim. If both an embedded variant and an explicit `--gguf-variant` are given and they disagree, the command fails with a clear error. * Studio: register `unsloth run` as alias for `unsloth studio run` Top-level `unsloth run --model ...` is now equivalent to `unsloth studio run --model ...`. Same context_settings, so unknown flags continue to pass through to llama-server. * Studio: let users override soft-managed llama-server flags from CLI Trims the denylist to flags Studio fundamentally cannot share with the user (model identity, --host/--port/--path/--api-prefix, --api-key, --ssl-*, --webui, --models-*). Soft-managed flags -- -c/--ctx-size, --parallel, --flash-attn, --no-context-shift, --jinja, -ngl, -t/--threads, --fit* -- now pass through and override Studio's auto-set version via llama.cpp's last-wins CLI parsing. Lets users tune their run on the spot: unsloth run --model X -c 131072 --parallel 1 --threads 32 * Studio: accept `-hf` / `-hfr` / `--hf-repo` as aliases for `--model` Matches llama-server's `-hf <repo>:<quant>` spelling so users coming from llama.cpp can use the same flag. Typer claims the aliases before the pass-through validator runs, so the HTTP-API denylist on those flags is unaffected. unsloth run -hf unsloth/gpt-oss-20b-GGUF:UD-Q4_K_XL
69 lines
2.4 KiB
Python
69 lines
2.4 KiB
Python
"""Tests that ``unsloth run`` is registered as a top-level alias for
|
|
``unsloth studio run``.
|
|
|
|
AST-based to avoid importing ``unsloth_cli`` (which pulls in the heavy
|
|
training stack) at test-collection time.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import ast
|
|
from pathlib import Path
|
|
|
|
_CLI_INIT = Path(__file__).resolve().parents[2] / "unsloth_cli" / "__init__.py"
|
|
|
|
|
|
def _module_calls(source: str):
|
|
tree = ast.parse(source)
|
|
for node in ast.walk(tree):
|
|
if isinstance(node, ast.Call):
|
|
yield node
|
|
|
|
|
|
def test_top_level_run_alias_registered():
|
|
"""`app.command("run", ...)` must be invoked with studio_run as its target."""
|
|
source = _CLI_INIT.read_text()
|
|
|
|
# Find ``app.command("run", ...)`` call -- the decorator-call form.
|
|
found_decorator_call = False
|
|
for call in _module_calls(source):
|
|
# Match ``app.command(...)`` syntactically.
|
|
if not (
|
|
isinstance(call.func, ast.Attribute)
|
|
and call.func.attr == "command"
|
|
and isinstance(call.func.value, ast.Name)
|
|
and call.func.value.id == "app"
|
|
):
|
|
continue
|
|
# Decorator-call form has a string literal "run" as the first
|
|
# positional or as keyword ``name="run"``.
|
|
first_pos = call.args[0] if call.args else None
|
|
keyword_name = next(
|
|
(kw.value for kw in call.keywords if kw.arg == "name"), None
|
|
)
|
|
is_run = (isinstance(first_pos, ast.Constant) and first_pos.value == "run") or (
|
|
isinstance(keyword_name, ast.Constant) and keyword_name.value == "run"
|
|
)
|
|
if is_run:
|
|
found_decorator_call = True
|
|
break
|
|
assert (
|
|
found_decorator_call
|
|
), 'Expected `app.command("run", ...)` registration in unsloth_cli/__init__.py'
|
|
|
|
|
|
def test_studio_run_imported_for_alias():
|
|
"""The alias must wire up to the studio.run function, not redefine it."""
|
|
source = _CLI_INIT.read_text()
|
|
tree = ast.parse(source)
|
|
has_import = False
|
|
for node in ast.walk(tree):
|
|
if not isinstance(node, ast.ImportFrom):
|
|
continue
|
|
if node.module != "unsloth_cli.commands.studio":
|
|
continue
|
|
for alias in node.names:
|
|
if alias.name == "run":
|
|
has_import = True
|
|
break
|
|
assert has_import, "Expected `from unsloth_cli.commands.studio import run` in unsloth_cli/__init__.py"
|